ClawHub
Back to skill

Security audit

Meteora Liquidity Analyst

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only Meteora data helper that queries public liquidity APIs and does not request wallet access, credentials, installs, or transaction authority.

Install this only if you want your agent to make live requests to Meteora public API endpoints for DeFi research. Treat APR, liquidity, and pool recommendations as informational, and specify Meteora/DLMM/DAMM when asking broad Solana liquidity questions to avoid misrouting.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation metadata is broad enough to trigger on generic Solana liquidity, AMM comparison, or token-search requests that are not necessarily Meteora-specific. Over-broad routing can cause the agent to invoke this skill in the wrong context, leading to unnecessary external API calls and misleading domain-specific answers presented as applicable more generally.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The 'When to Activate' section lists positive triggers but does not define exclusion criteria, so the skill may be selected for loosely related liquidity-analysis questions outside Meteora. In an agentic system, ambiguous activation boundaries increase the chance of misrouting, which can produce inaccurate advice and expand external-data exposure beyond user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal